oumi-ai /oumi

Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!

★ 9,433⑂ 798👁 61⑃ 2,606● 117▤ 27
PythonApache-2.0Created 2024-05-07oumi.ai
下载:v0.9v0.9 ↓0.92026-09-16
+0
日增长
9,433
stars
798
forks
61
watchers
2,606
prs
117
issues
27
releases

README

!Oumi Logo














 Everything you need to build state-of-the-art foundation models, end-to-end


  
    
  


 🔥 News

- [2026/09] Oumi v0.9 released: an end-to-end stack for agentic, tool-using models, with tool-calling SFT/DPO, executable tool environments, GRPO over any Oumi environment with verl, and a multi-criteria RubricJudge.
- [2026/08] Extended GRPO reinforcement learning to support tool use
- [2026/07] Added support for tools, environments (simulated, lookup, database), and agentic data synthesis
- [2026/06] Added support for the Gemma 4 model family
- [2026/06] Added partial-failure support across inference, judging, and data synthesis
- [2026/05] Oumi v0.8 released with oumi deploy CLI for dedicated inference endpoints, an oumi-mcp MCP server for Claude/Cursor integration, batch API support across Anthropic/Fireworks/Together, and Transformers v5 / TRL / vLLM dependency upgrades
- [2026/03] Upgraded to Transformers v5, TRL v0.30, vLLM v0.19, and veRL v0.7 compatibility
- [2026/03] New oumi deploy command for deploying Oumi models to dedicated inference endpoints on Fireworks and Parasail
- [2026/03] Added support for the Qwen3.5 model family
- [2026/02] Preview of using the Oumi Platform and Lambda to fine-tune and deploy a 4B model for user intent classification
- [2026/02] Lambda and Oumi partner for end-to-end custom model development
- [2026/01] Oumi v0.7 released with Python 3.14 and PyTorch 2.9 support, Fireworks and OpenRouter inference engines, and rule-based evaluation judges
- [2025/12] Oumi v0.6.0 released with Python 3.13 support, oumi analyze CLI command, TRL 0.26+ support, and more
- [2025/12] WeMakeDevs AI Agents Assemble Hackathon: Oumi webinar on Finetuning for Text-to-SQL
- [2025/12] Oumi co-sponsors WeMakeDevs AI Agents Assemble Hackathon with over 2000 project submissions
- [2025/11] Oumi v0.5.0 released with advanced data synthesis, hyperparameter tuning automation, support for OpenEnv, and more


Older updates

- [2025/11] Example notebook to perform RLVF fine-tuning with OpenEnv, an open source library from the Meta PyTorch team for creating, deploying, and distributing agentic RL environments
- [2025/10] Oumi v0.4.1 and v0.4.2 released] with support for Qwen3-VL and Transformers v4.56, data synthesis documentation and examples, and many bug fixes
- [2025/09] Oumi v0.4.0 released with DeepSpeed support, a Hugging Face Hub cache management tool, KTO/Vision DPO trainer support
- [2025/08] Training and inference support for OpenAI's gpt-oss-20b and gpt-oss-120b: recipes here
- [2025/08] Aug 14 Webinar - OpenAI's gpt-oss: Separating the Substance from the Hype.
- [2025/08] Oumi v0.3.0 released with model quantization (AWQ), an improved LLM-as-a-Judge API, and Adaptive Inference
- [2025/07] Recipe for Qwen3 235B
- [2025/07] July 24 webinar: "Training a State-of-the-art Agent LLM with Oumi + Lambda"
- [2025/06] Oumi v0.2.0 released with support for GRPO fine-tuning, a plethora of new model support, and much mo

Top issues

Latest release

v0.9 v0.9 2026-09-16
Oumi v0.9 Release Notes

This release makes Oumi an end-to-end stack for agentic, tool-using models: you can now train on tool-calling data, execute tool calls against real environments (databases, HTTP endpoints, deterministic lookups, and model-simulated tools), synthesize multi-turn tool conversations, and run GRPO/RL over any of those environments with verl. It also adds a multi-criteria RubricJudge, partial-failure-tolerant inference/synthesis/judging, a Modal GPU launcher and SkyPilot-routed Slurm, and new Gemma 4 recipes.

 Highlights

 🛠️ Tool-use training

Train models to call

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON